# This Python 3 environment comes with many helpful analytics libraries installed
# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python
# For example, here's several helpful packages to load

import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import re
import plotly.express as px
import matplotlib.pyplot as plt
import os
# Input data files are available in the read-only "../input/" directory
# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

marvel=pd.read_csv("Marvel_Movies.csv")
marvel

	name	ID	ALIGN	EYE	HAIR	SEX	GSM	ALIVE	APPEARANCES	FIRST APPEARANCE	Year
0	Spider-Man (Peter Parker)	Secret Identity	Good Characters	Hazel Eyes	Brown Hair	Male Characters	NaN	Living Characters	4043.0	Aug-62	1962.0
1	Captain America (Steven Rogers)	Public Identity	Good Characters	Blue Eyes	White Hair	Male Characters	NaN	Living Characters	3360.0	Mar-41	1941.0
2	Wolverine (James \"Logan\" Howlett)	Public Identity	Neutral Characters	Blue Eyes	Black Hair	Male Characters	NaN	Living Characters	3061.0	Oct-74	1974.0
3	Iron Man (Anthony \"Tony\" Stark)	Public Identity	Good Characters	Blue Eyes	Black Hair	Male Characters	NaN	Living Characters	2961.0	Mar-63	1963.0
4	Thor (Thor Odinson)	No Dual Identity	Good Characters	Blue Eyes	Blond Hair	Male Characters	NaN	Living Characters	2258.0	Nov-50	1950.0
...	...	...	...	...	...	...	...	...	...	...	...
16371	Ru'ach (Earth-616)	No Dual Identity	Bad Characters	Green Eyes	No Hair	Male Characters	NaN	Living Characters	NaN	NaN	NaN
16372	Thane (Thanos' son) (Earth-616)	No Dual Identity	Good Characters	Blue Eyes	Bald	Male Characters	NaN	Living Characters	NaN	NaN	NaN
16373	Tinkerer (Skrull) (Earth-616)	Secret Identity	Bad Characters	Black Eyes	Bald	Male Characters	NaN	Living Characters	NaN	NaN	NaN
16374	TK421 (Spiderling) (Earth-616)	Secret Identity	Neutral Characters	NaN	NaN	Male Characters	NaN	Living Characters	NaN	NaN	NaN
16375	Yologarch (Earth-616)	NaN	Bad Characters	NaN	NaN	NaN	NaN	Living Characters	NaN	NaN	NaN

16376 rows × 11 columns

marvel.shape

(16376, 11)

marvel.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 16376 entries, 0 to 16375
Data columns (total 11 columns):
 #   Column            Non-Null Count  Dtype  
---  ------            --------------  -----  
 0   name              16376 non-null  object 
 1   ID                12606 non-null  object 
 2   ALIGN             13564 non-null  object 
 3   EYE               6609 non-null   object 
 4   HAIR              12112 non-null  object 
 5   SEX               15522 non-null  object 
 6   GSM               90 non-null     object 
 7   ALIVE             16373 non-null  object 
 8   APPEARANCES       15280 non-null  float64
 9   FIRST APPEARANCE  15561 non-null  object 
 10  Year              15561 non-null  float64
dtypes: float64(2), object(9)
memory usage: 1.4+ MB

Разделение реальных имён и ников/названий героев

nicknames=[]
names=[]
for name in marvel.name:
   match= re.search("\((?:(?!\))(?:.|\n))*\)",name)
   if match:
    nickname=name[match.start()+1:match.end()-1]
    newname=name.replace(name[match.start():match.end()],"")
    names.append(newname)
    nicknames.append(nickname)
   else:
    names.append(np.nan)
    nicknames.append(np.nan)

marvel['nicknames']=names
marvel['name']=nicknames
marvel

	name	ID	ALIGN	EYE	HAIR	SEX	GSM	ALIVE	APPEARANCES	FIRST APPEARANCE	Year	nicknames
0	Peter Parker	Secret Identity	Good Characters	Hazel Eyes	Brown Hair	Male Characters	NaN	Living Characters	4043.0	Aug-62	1962.0	Spider-Man
1	Steven Rogers	Public Identity	Good Characters	Blue Eyes	White Hair	Male Characters	NaN	Living Characters	3360.0	Mar-41	1941.0	Captain America
2	James \"Logan\" Howlett	Public Identity	Neutral Characters	Blue Eyes	Black Hair	Male Characters	NaN	Living Characters	3061.0	Oct-74	1974.0	Wolverine
3	Anthony \"Tony\" Stark	Public Identity	Good Characters	Blue Eyes	Black Hair	Male Characters	NaN	Living Characters	2961.0	Mar-63	1963.0	Iron Man
4	Thor Odinson	No Dual Identity	Good Characters	Blue Eyes	Blond Hair	Male Characters	NaN	Living Characters	2258.0	Nov-50	1950.0	Thor
...	...	...	...	...	...	...	...	...	...	...	...	...
16371	Earth-616	No Dual Identity	Bad Characters	Green Eyes	No Hair	Male Characters	NaN	Living Characters	NaN	NaN	NaN	Ru'ach
16372	Thanos' son	No Dual Identity	Good Characters	Blue Eyes	Bald	Male Characters	NaN	Living Characters	NaN	NaN	NaN	Thane (Earth-616)
16373	Skrull	Secret Identity	Bad Characters	Black Eyes	Bald	Male Characters	NaN	Living Characters	NaN	NaN	NaN	Tinkerer (Earth-616)
16374	Spiderling	Secret Identity	Neutral Characters	NaN	NaN	Male Characters	NaN	Living Characters	NaN	NaN	NaN	TK421 (Earth-616)
16375	Earth-616	NaN	Bad Characters	NaN	NaN	NaN	NaN	Living Characters	NaN	NaN	NaN	Yologarch

16376 rows × 12 columns

Статистика персонажей по полу

marvel['SEX'] = marvel['SEX'].fillna("Не определён")
gendre=marvel.SEX.value_counts()
px.bar(gendre,text_auto='.4s', labels={'index':'Genders','variable':'Quantity'})

marvel.SEX.unique()

array(['Male Characters', 'Female Characters', 'Genderfluid Characters',
       'Agender Characters', 'Не определён'], dtype=object)

len(marvel[marvel['SEX']=="Male Characters"])/len(marvel) * 100
genderValues = marvel.SEX.unique()
total = marvel['SEX'].value_counts().sum()
print("Процентаж персонажей по полу")
gendrePercentage = pd.Series(dtype='float64')
for v in genderValues:
    p = len(marvel[marvel['SEX']==v])/len(marvel) * 100
    gendrePercentage = pd.concat([gendrePercentage, pd.Series(data={v: p}, index=[v])])
    print(v + ": " + str(round(p,2)) + " %")

px.bar(gendrePercentage.sort_values(ascending=False),text_auto='.4s', labels={'index':'Genders','variable':'Percentage'})

Процентаж персонажей по полу
Male Characters: 71.07 %
Female Characters: 23.43 %
Genderfluid Characters: 0.01 %
Agender Characters: 0.27 %
Не определён: 5.21 %

Соотношение живых персонажей и поверженных + неизвестный статус(?)

marvel.ALIVE.unique()

array(['Living Characters', 'Deceased Characters', nan], dtype=object)

print("ALIVE - " + str(len(marvel[marvel['ALIVE']=="Living Characters"])/len(marvel)))
print("Deceased Characters - " + str(len(marvel[marvel['ALIVE']=="Deceased Characters"])/len(marvel)))
print("Unknown status - " + str(len(marvel[marvel['ALIVE'].isnull()])/len(marvel)))

ALIVE - 0.7699071812408402
Deceased Characters - 0.22990962383976551
Unknown status - 0.00018319491939423546

Появление количества новых персонажей по году

years=marvel.Year.value_counts().sort_index()
px.line(years)

ТОП-10 персонажей, которые упоминались чаще всего

fig = px.bar(data_frame=marvel.head(10), x='nicknames', y='APPEARANCES', title='ТОП - 10 персонажей по популярности',
             color='APPEARANCES',
                 color_continuous_scale=["orange", "red",
                                         "green", "blue",
                                         "purple"])
fig.show()

Статистика по глазам

eye=marvel.EYE.value_counts().sort_values().head()
px.bar(eye,orientation='h')

Статистика по волосам

hair=marvel.HAIR.value_counts().sort_values(ascending=False)
px.bar(hair)

Статистика по внешности (сгруппированная)

marvel.groupby(['EYE','HAIR']).count().name.nlargest(10)

EYE         HAIR      
Brown Eyes  Black Hair    824
            Brown Hair    655
Blue Eyes   Blond Hair    648
            Black Hair    391
            Brown Hair    294
Black Eyes  Black Hair    257
Red Eyes    No Hair       186
Green Eyes  No Hair       153
Brown Eyes  Bald          137
Blue Eyes   White Hair    132
Name: name, dtype: int64

dfg=marvel.groupby(['EYE','HAIR']).count().name.nlargest(10)
ax = dfg.unstack(level=0).plot(kind='bar', subplots=True, rot=40, figsize=(20, 20), layout=(6, 5))
plt.show()